Saved in:
Bibliographic Details
Main Authors: Liu, Junyu, Jones, R. Kenny, Ritchie, Daniel
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.03004
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916949494071296
author Liu, Junyu
Jones, R. Kenny
Ritchie, Daniel
author_facet Liu, Junyu
Jones, R. Kenny
Ritchie, Daniel
contents We present PartComposer: a framework for part-level concept learning from single-image examples that enables text-to-image diffusion models to compose novel objects from meaningful components. Existing methods either struggle with effectively learning fine-grained concepts or require a large dataset as input. We propose a dynamic data synthesis pipeline generating diverse part compositions to address one-shot data scarcity. Most importantly, we propose to maximize the mutual information between denoised latents and structured concept codes via a concept predictor, enabling direct regulation on concept disentanglement and re-composition supervision. Our method achieves strong disentanglement and controllable composition, outperforming subject and part-level baselines when mixing concepts from the same, or different, object categories.
format Preprint
id arxiv_https___arxiv_org_abs_2506_03004
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PartComposer: Learning and Composing Part-Level Concepts from Single-Image Examples
Liu, Junyu
Jones, R. Kenny
Ritchie, Daniel
Graphics
Computer Vision and Pattern Recognition
We present PartComposer: a framework for part-level concept learning from single-image examples that enables text-to-image diffusion models to compose novel objects from meaningful components. Existing methods either struggle with effectively learning fine-grained concepts or require a large dataset as input. We propose a dynamic data synthesis pipeline generating diverse part compositions to address one-shot data scarcity. Most importantly, we propose to maximize the mutual information between denoised latents and structured concept codes via a concept predictor, enabling direct regulation on concept disentanglement and re-composition supervision. Our method achieves strong disentanglement and controllable composition, outperforming subject and part-level baselines when mixing concepts from the same, or different, object categories.
title PartComposer: Learning and Composing Part-Level Concepts from Single-Image Examples
topic Graphics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.03004